Effect of the Maxent model’s complexity on the prediction of species potential distributions

ZHU Gengping1 QIAO Huijie2

(1.Tianjin Key Laboratory of Animal and Plant Resistance, College of Life Sciences, Tianjin Normal University, Tianjin 300387)
(2.Institute of Zoology, Chinese Academy of Sciences, Beijing 100101)
【Knowledge Link】molecular systematics; species; habitat

【Abstract】Ecological niche modeling (ENM) is widely used in the study of biological invasions and conservation biology. Maxent is the most popular algorithm and is being increasingly used to estimate species’ realized and potential distributions. Most modelers use the default Maxent setting to fit niche models, which originated from an earlier study containing 266 species, with the purpose of seeking their realized distributions. However, recent studies have shown that Maxent uses a complex machine learning method. It is sensitive to sampling bias and tends to overfit training data, and is only transferrable at low thresholds. Default settings based on Maxent outputs are sometimes not reliable, making it difficult to interpret. Using Halyomorpha halys and classical modeling approaches (i.e., niche models that were calibrated in native East Asia and transferred to North America), we tested the complexity and performance of the Maxent model under different settings of regulation multipliers and feature combinations, and chose a fine-tuned setting with the lowest complexity. We then compared the response curves and model interpolative and extrapolative validations between models calibrated using default and fine-tuned settings. Our purpose was to explore the effects of the model’s complexity on niche model performance in order to improve the development and application of Maxent in China. We argue that selection of environmental variables is crucial for model calibration, which should include ecological relevance and spatial correlation. Reducing sampling bias and delimitating a proper geographic background, together with the comparison of response curves and complexity of Maxent models built under different settings, is very important for fitting a good niche model. In the case of H. halys, the default and fine-tuned settings are different, however the response curve is much smoother in the fine-tuned model, and the omission error is lower in introduced areas when compared to default model, suggesting that the fine-tuned model reflects the response of H. halys to environmental factors more reasonably and precisely predicts the potential distribution.

【Keywords】 ecological niche model; Maxent; model complexity; transferability; realized distribution; potential distribution;


【Funds】 National Natural Science Fund of China (31401962) Talent Introduction Fund Project of Tianjin Normal University (5RL127) Tianjin 131 Innovative Talents Cultivation Project (ZX110204) More Than Thousands of High-Level Talent Project in Three Years in Tianjin (5KQM110030)

Download this article


    Ahmed SE, McI nerny G, O’Hara K, Harper R, Salido L, Em-mott S, Joppa LN (2015) Scientists and software-surveying the species distribution modelling community. Diversity and Distributions, 21, 258–267.

    Akaike H (1973) Information theory and an extension of the maximum likelihood principle. In: 2nd International Symposium on Information Theory (eds Petrov BN, Csáki F), pp. 267–281. Akadémiai Kiadó, Budapest.

    Barbosa FG, Schneck F (2015) Characteristics of the top-cited papers in species distribution predictive models. Ecological Modelling, 313, 77–83.

    Elith J, Phillips SJ, Hastie T, Dudík D, Chee YE, Yates CJ (2010) A statistical explanation of Max Ent for ecologists. Diversity and Distributions, 17, 43–57.

    Hijmans RJ, Cameron SE, Parra JL, Jones PG, Jarvis A (2005) Very high resolution interpolated climate surfaces for global land areas. International Journal of Climatology, 25, 1965–1978.

    JiménezValverde A, Peterson AT, Soberón J, Overton JM, Aragón P, Lobo JM (2011) Use of niche models in invasive species risk assessments. Biological Invasions, 13, 2785–2797.

    Kearney MR, Wintle BA, Porter WP (2010) Correlative and mechanistic models of species distribution provide congruent forecasts under climate change. Conservation Letters, 3, 203–213.

    Kriticos DJ, Webber BL, Leriche A, Ota N, Macadam I, Bathols J, Scott JK (2011) CliM ond: global high resolution historical and future scenario climate surfaces for bioclimatic modeling. Methods in Ecology and Evolution, 3, 53–64.

    Muscarella R, Galante PJ, Soley-Guardia M, Boria RA, Kass JM, Uriarte M, Anderson RP (2014) ENMeval: An R package for conducting spatially independent evaluations and estimating optimal model complexity for MAXENT ecological niche models. Methods in Ecology and Evolution, 5, 1198–1205.

    Peterson AT, PapeşM, Soberón J (2008) Rethinking receiver operating characteristic analysis applications in ecological niche modeling. Ecological Modelling, 213, 63–72.

    Peterson AT, Soberón J (2012) Species distribution modeling and ecological niche modeling:getting the concepts right. Natureza & Conservacao, 10, 102–107.

    Peterson AT, Soberón J, Pearson RG, Anderson RP, Nakamura M, MartínezMeyer E, Araújo MB (2011) Ecological Niches and Geographical Distributions. Princeton University Press, New Jersey.

    Phillips SJ, Anderson RP, Schapire RE (2006) Maximum entropy modeling of species geographic distributions. Ecological Modelling, 190, 231–259.

    Phillips SJ, Dudík MM (2008) Modeling of species distributions with Maxent:new extensions and a comprehensive evaluation. Ecography, 31, 161–175.

    Qiao HJ, Hu JH, Huang JH (2013) Theoretical basis, future directions, and challenges for ecological niche models. Scientia Sinica Vitae, 43, 915–927 (in Chinese with English abstract).

    Qiao HJ, Soberón J, Peterson AT (2015) No silver bullets in correlative ecological niche modeling: insights from testing among many potential algorithms for niche estimation. Methods in Ecology and Evolution, 6, 1126–1136.

    Soberón J, Peterson AT (2005) Interpretation of models of fundamental ecological niches and species’ distributional areas. Biodiversity Informatics, 2, 1–10.

    Vaz UL, Cunha HF, Nabout JC (2015) Trends and biases in global scientific literature about ecological niche models. Brazilian Journal of Biology, 75, 17–24.

    Warren DL, Seifert SN (2011) Ecological niche modeling in Maxent:the importance of model complexity and the performance of model selection criteria. Ecology Applications, 21, 335–342.

    Warren DL, Wright AN, Seifert SN, Shaffer HB (2014) Incorporating model complexity and spatial sampling bias into ecological niche models of climate change risks faced by 90 California vertebrate species of concern. Diversity and Distributions, 20, 334–343.

    Zhu GP, Bu WJ, Gao YB, Liu GQ (2012) Potential geographic distribution of brown marmorated stink bug invasion (Halyomorpha halys) . PLo S ONE, 7, e31246.

    Zhu GP, Gao YB, Zhu L (2013) Delimiting the coastal geographic background to predict potential distribution of Spar-tina alterniflora. Hydrobiologia, 717, 177–187.

    Zhu GP, Redei D, Kment P, Bu WJ (2014) Effect of geographic background and equilibrium state on niche model transferability: predicting areas of invasion of Leptoglossus occidentalis. Biological Invasions, 16, 1069–1081.

    Zhu GP, Gariepy TD, Haye T, Bu WJ (2016) Patterns of niche filling and expansion across the invaded ranges of Halyomorpha halys in North America and Europe. Journal of Pest Science, doi:10.1007/s10340-016-0786-z.

    Zhu GP, Liu GQ, Bu WJ, Gao YB (2013) Ecological niche modeling and its applications in biodiversity conservation. Biodiversity Science, 21, 90–98 (in Chinese with English abstract).

    Zhu GP, Liu Q, Gao YB (2014) Improving ecological niche model transferability to predict the potential distribution of invasive exotic species. Biodiversity Science, 22, 223–230 (in Chinese with English abstract).

This Article


CN: 11-3247/Q

Vol 24, No. 10, Pages 1189-1196

October 2016


Article Outline



  • 1 Materials and methods
  • 2 Results
  • 3 Discussion
  • References